Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shi, Yujun, Liang, Jian, Zhang, Wenqing, Tan, Vincent Y. F., Bai, Song
Format:	Preprint
Published:	2022
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Understanding and Mitigating Hyperbolic Dimensional Collapse in Graph Contrastive Learning
by: Zhang, Yifei, et al.
Published: (2023)

Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning
by: Shi, Yujun, et al.
Published: (2021)

DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing
by: Shi, Yujun, et al.
Published: (2023)

Heterogeneity-Oblivious Robust Federated Learning
by: Zhang, Weiyao, et al.
Published: (2025)

Towards Understanding Why FixMatch Generalizes Better Than Supervised Learning
by: Li, Jingyang, et al.
Published: (2024)

FedFixer: Mitigating Heterogeneous Label Noise in Federated Learning
by: Ji, Xinyuan, et al.
Published: (2024)

The Collapse of Heterogeneity in Silicon Philosophers
by: Shi, Yuanming, et al.
Published: (2026)

Understanding and Improving Model Averaging in Federated Learning on Heterogeneous Data
by: Zhou, Tailin, et al.
Published: (2023)

Federated Reinforcement Learning with Constraint Heterogeneity
by: Jin, Hao, et al.
Published: (2024)

FlexFed: Mitigating Catastrophic Forgetting in Heterogeneous Federated Learning in Pervasive Computing Environments
by: Alosaime, Sara, et al.
Published: (2025)

Adaptive Guidance for Local Training in Heterogeneous Federated Learning
by: Zhang, Jianqing, et al.
Published: (2024)

Understanding DNNs in Feature Interaction Models: A Dimensional Collapse Perspective
by: Wang, Jiancheng, et al.
Published: (2026)

Mitigating Group Bias in Federated Learning for Heterogeneous Devices
by: Selialia, Khotso, et al.
Published: (2023)

Towards Robust Knowledge Removal in Federated Learning with High Data Heterogeneity
by: Santi, Riccardo, et al.
Published: (2025)

Towards Understanding Neural Collapse: The Effects of Batch Normalization and Weight Decay
by: Pan, Leyan, et al.
Published: (2023)

Towards Robust Federated Multimodal Graph Learning under Modality Heterogeneity
by: Zhang, Sirui, et al.
Published: (2026)

FedQuad: Federated Stochastic Quadruplet Learning to Mitigate Data Heterogeneity
by: Goksu, Ozgu, et al.
Published: (2025)

Towards Understanding Transformers in Learning Random Walks
by: Shi, Wei, et al.
Published: (2025)

Invariant Federated Learning for Edge Intelligence: Mitigating Heterogeneity and Asynchrony via Exit Strategy and Invariant Penalty
by: Hao, Ziruo, et al.
Published: (2025)

On the Robustness of Neural Collapse and the Neural Collapse of Robustness
by: Su, Jingtong, et al.
Published: (2023)

Continuous First, Discrete Later: VQ-VAEs Without Dimensional Collapse
by: Zhao, Xinyu, et al.
Published: (2026)

FedKL: Tackling Data Heterogeneity in Federated Reinforcement Learning by Penalizing KL Divergence
by: Xie, Zhijie, et al.
Published: (2022)

Adversarial Combinatorial Bandits with Switching Costs
by: Dong, Yanyan, et al.
Published: (2024)

Towards Privacy-Preserving and Heterogeneity-aware Split Federated Learning via Probabilistic Masking
by: Wang, Xingchen, et al.
Published: (2025)

FedLGA: Towards System-Heterogeneity of Federated Learning via Local Gradient Approximation
by: Li, Xingyu, et al.
Published: (2021)

Heterogeneity-Guided Client Sampling: Towards Fast and Efficient Non-IID Federated Learning
by: Chen, Huancheng, et al.
Published: (2023)

Understanding and Mitigating the High Computational Cost in Path Data Diffusion
by: Shi, Dingyuan, et al.
Published: (2025)

HARMONY: Bridging the Personalization-Generalization Gap by Mitigating Representation Skew in Heterogeneous Split Federated Learning
by: Youn, Jiseok, et al.
Published: (2026)

Achieving Linear Speedup in Asynchronous Federated Learning with Heterogeneous Clients
by: Wang, Xiaolu, et al.
Published: (2024)

Widening the Network Mitigates the Impact of Data Heterogeneity on FedAvg
by: Jian, Like, et al.
Published: (2025)

Understanding Representation of Deep Equilibrium Models from Neural Collapse Perspective
by: Sun, Haixiang, et al.
Published: (2024)

Towards Understanding Adversarial Transferability in Federated Learning
by: Li, Yijiang, et al.
Published: (2023)

An Enhanced Federated Prototype Learning Method under Domain Shift
by: Kuang, Liang, et al.
Published: (2024)

Client Selection for Federated Policy Optimization with Environment Heterogeneity
by: Xie, Zhijie, et al.
Published: (2023)

Federated Reinforcement Learning in Heterogeneous Environments
by: Hwang, Ukjo, et al.
Published: (2025)

The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward
by: Li, Long, et al.
Published: (2025)

Preventing Rank Collapse in Federated Low-Rank Adaptation with Client Heterogeneity
by: Wu, Fei, et al.
Published: (2026)

Memory-adaptive Depth-wise Heterogeneous Federated Learning
by: Zhang, Kai, et al.
Published: (2023)

A Unified Solution to Diverse Heterogeneities in One-shot Federated Learning
by: Bai, Jun, et al.
Published: (2024)

From Risk to Resilience: Towards Assessing and Mitigating the Risk of Data Reconstruction Attacks in Federated Learning
by: Xu, Xiangrui, et al.
Published: (2025)